Hostname: page-component-8448b6f56d-mp689 Total loading time: 0 Render date: 2024-04-24T16:14:34.677Z Has data issue: false hasContentIssue false
  • English
  • Français

Ingredients of intelligence: From classic debates to an engineering roadmap

Published online by Cambridge University Press:  10 November 2017

Brenden M. Lake ,
Tomer D. Ullman ,
Joshua B. Tenenbaum  and
Samuel J. Gershman
Brenden M. Lake
Affiliation:
Department of Psychology and Center for Data Science, New York University, New York, NY 10011. brenden@nyu.eduhttp://cims.nyu.edu/~brenden/
Tomer D. Ullman
Affiliation:
Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA 02139. tomeru@mit.edujbt@mit.eduhttp://www.mit.edu/~tomeru/http://web.mit.edu/cocosci/josh.html The Center for Brains Minds and Machines, Cambridge, MA 02139
Joshua B. Tenenbaum
Affiliation:
Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA 02139. tomeru@mit.edujbt@mit.eduhttp://www.mit.edu/~tomeru/http://web.mit.edu/cocosci/josh.html The Center for Brains Minds and Machines, Cambridge, MA 02139
Samuel J. Gershman
Affiliation:
The Center for Brains Minds and Machines, Cambridge, MA 02139 Department of Psychology and Center For Brain Science, Harvard University, Cambridge, MA 02138. gershman@fas.harvard.eduhttp://gershmanlab.webfactional.com/index.html
Get access Rights & Permissions [Opens in a new window]

Abstract

We were encouraged by the broad enthusiasm for building machines that learn and think in more human-like ways. Many commentators saw our set of key ingredients as helpful, but there was disagreement regarding the origin and structure of those ingredients. Our response covers three main dimensions of this disagreement: nature versus nurture, coherent theories versus theory fragments, and symbolic versus sub-symbolic representations. These dimensions align with classic debates in artificial intelligence and cognitive science, although, rather than embracing these debates, we emphasize ways of moving beyond them. Several commentators saw our set of key ingredients as incomplete and offered a wide range of additions. We agree that these additional ingredients are important in the long run and discuss prospects for incorporating them. Finally, we consider some of the ethical questions raised regarding the research program as a whole.

Type
Authors' Response
Information
Behavioral and Brain Sciences , Volume 40 , 2017 , e281
Check for updates
Copyright
Copyright © Cambridge University Press 2017 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Aurelius, M. (1937) Meditations, transl. Long, G.. P. F. Collier & Son.Google Scholar
Bahdanau, D., Cho, K. & Bengio, Y. (2015) Neural machine translation by jointly learning to align and translate. Presented at the International Conference on Learning Representations (ICLR), San Diego, CA, May 7–9, 2015. arXiv preprint 1409.0473. Available at: http://arxiv.org/abs/1409.0473v3.Google Scholar
Baker, C. L., Jara-Ettinger, J., Saxe, R. & Tenenbaum, J. B. (2017). Rational quantitative attribution of beliefs, desires and percepts in human mentalizing. Nature Human Behaviour 1:0064.Google Scholar
Baker, C. L., Saxe, R. & Tenenbaum, J. B. (2009) Action understanding as inverse planning. Cognition 113(3):329–49.Google Scholar
Battaglia, P. W., Hamrick, J. B. & Tenenbaum, J. B. (2013) Simulation as an engine of physical scene understanding. Proceedings of the National Academy of Sciences of the United States of America 110(45):18327–32.Google Scholar
Carey, S. (2009) The origin of concepts. Oxford University Press.Google Scholar
Chen, X. & Yuille, A. L. (2014) Articulated pose estimation by a graphical model with image dependent pairwise relations. In: Advances in neural information processing systems 27 (NIPS 2014), ed. Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N. D. & Weinberger, K. Q., pp. 1736–44. Neural Information Processing Systems Foundation.Google Scholar
Cook, C., Goodman, N. D. & Schulz, L. E. (2011) Where science starts: Spontaneous experiments in preschoolers' exploratory play. Cognition 120(3):341–49.Google Scholar
Corriveau, K. H., Kim, E., Song, G. & Harris, P. L. (2013) Young children's deference to a consensus varies by culture and judgment setting. Journal of Cognition and Culture 13(3–4):367–81.CrossRefGoogle Scholar
Davoodi, T., Corriveau, K. H. & Harris, P. L. (2016) Distinguishing between realistic and fantastical figures in Iran. Developmental Psychology 52(2):221.Google Scholar
Doshi-Velez, F. & Kim, B. (2017) A roadmap for a rigorous science of interpretability. arXiv preprint 1702.08608. Available at: https://arxiv.org/abs/1702.08608.Google Scholar
Eslami, S. M., Heess, N., Weber, T., Tassa, Y., Kavukcuoglu, K. & Hinton, G. E. (2016) Attend, infer, repeat: Fast scene understanding with generative models. Presented at the 2016 Neural Information Processing Systems conference, Barcelona, Spain, December 5–10, 2016. In: Advances in Neural Information Processing Systems 29 (NIPS 2016), ed. Lee, D. D., Sugiyama, M., Luxburg, U. V., Guyon, I. & Garnett, R., pp. 3225–33. Neural Information Processing Systems Foundation.Google Scholar
Goodman, N. D., Tenenbaum, J. B., Feldman, J. & Griffiths, T. L. (2008) A rational analysis of rule-based concept learning. Cognitive Science 32(1):108–54.Google Scholar
Goodman, N. D., Tenenbaum, J. B. & Gerstenberg, T. (2015). Concepts in a probabilistic language of thought. In: The conceptual mind: New directions in the study of concepts, ed. Margolis, E. & Laurence, S., pp. 623–54. MIT Press.Google Scholar
Goodman, N. D., Ullman, T. D. & Tenenbaum, J. B. (2011) Learning a theory of causality. Psychological Review 118(1):110–19.CrossRefGoogle ScholarPubMed
Gopnik, A., Glymour, C., Sobel, D. M., Schulz, L. E., Kushnir, T. & Danks, D. (2004) A theory of causal learning in children: Causal maps and Bayes nets. Psychological Review 111(1):3–32.Google Scholar
Graves, A., Wayne, G. & Danihelka, I. (2014) Neural Turing machines. arXiv preprint 1410.5401v1. Available at: http://arxiv.org/abs/1410.5401v1.Google Scholar
Graves, A., Wayne, G., Reynolds, M., Harley, T., Danihelka, I., Grabska-Barwińska, A., Colmenarejo, S. G., Grefenstette, E., Ramalho, T., Agapiou, J., Badia, A. P., Hermann, K. M., Zwols, Y., Ostrovski, G., Cain, A., King, H., Summerfield, C., Blunsom, P., Kayukcuoglu, K. & Hassabis, D. (2016) Hybrid computing using a neural network with dynamic external memory. Nature 538(7626):471–76.Google Scholar
Gray, H. M., Gray, K. & Wegner, D. M. (2007) Dimensions of mind perception. Science 315(5812):619.CrossRefGoogle ScholarPubMed
Gray, K. & Wegner, D. M. (2012) Feeling robots and human zombies: Mind perception and the uncanny valley. Cognition 125(1):125–30.Google Scholar
Grefenstette, E., Hermann, K. M., Suleyman, M. & Blunsom, P. (2015). Learning to transduce with unbounded memory. Presented at the 2015 Neural Information Processing Systems conference. In: Advances in Neural Information Processing Systems 28, ed. Cortes, C., Lawrence, N. D., Lee, D. D., Sugiyama, M. & Garnett, R.. Neural Information Processing Systems Foundation.Google Scholar
Griffiths, T. L., Chater, N., Kemp, C., Perfors, A. & Tenenbaum, J. B. (2010) Probabilistic models of cognition: Exploring representations and inductive biases. Trends in Cognitive Sciences 14(8):357–64.CrossRefGoogle ScholarPubMed
Griffiths, T. L. & Tenenbaum, J. B. (2005) Structure and strength in causal induction. Cognitive Psychology 51(4):334–84.Google Scholar
Griffiths, T. L. & Tenenbaum, J. B. (2009) Theory-based causal induction. Psychological Review 116(4):661–716.CrossRefGoogle ScholarPubMed
Haslam, N. (2006) Dehumanization: An integrative review. Personality and Social Psychology Review 10(3):252–64.Google Scholar
Jain, A., Tompson, J., Andriluka, M., Taylor, G. W. & Bregler, C. (2014). Learning human pose estimation features with convolutional networks. Presented at the International Conference on Learning Representations (ICLR), Banff, Canada, April 14–16, 2014. arXiv preprint 1312.7302. Available at: https://arxiv.org/abs/1312.7302.Google Scholar
Kahou, S. E., Pal, C., Bouthillier, X., Froumenty, P., Gülçehre, Ç., Memisevic, R., Vincent, P., Courville, A. & Bengio, Y. (2013) Combining modality specific deep neural networks for emotion recognition in video. In: Proceedings of the 15th ACM International Conference on Multimodal Interaction, Koogee Beach, Sydney, Australia, pp. 543–50. ACM.Google Scholar
Kellman, P. J. & Spelke, E. S. (1983) Perception of partly occluded objects in infancy. Cognitive Psychology 15(4):483–524.Google Scholar
Kemp, C., Perfors, A. & Tenenbaum, J. B. (2007) Learning overhypotheses with hierarchical Bayesian models. Developmental Science 10(3):307–21.Google Scholar
Kemp, C. & Tenenbaum, J. B. (2008) The discovery of structural form. Proceedings of the National Academy of Sciences of the United States of America 105(31):10687–92.Google Scholar
Kiddon, C., Zettlemoyer, L. & Choi, Y. (2016). Globally coherent text generation with neural checklist models. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, Texas, November 1–5, 2016, pp. 329–39. Association for Computational Linguistics.Google Scholar
Krizhevsky, A., Sutskever, I. & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Presented at the 25th International Conference on Neural Information Processing Systems, Lake Tahoe, NV, December 3–6, 2012. In: Advances in Neural Information Processing Systems 25 (NIPS 2012), ed. Pereira, F., Burges, C. J. C., Bottou, L. & Weinberger, K. Q., pp. 1097–105. Neural Information Processing Systems Foundation.Google Scholar
Lake, B. M., Lawrence, N. D. & Tenenbaum, J. B. (2016) The emergence of organizing structure in conceptual representation. arXiv preprint 1611.09384. Available at: http://arxiv.org/abs/1611.09384.Google Scholar
Lake, B. M., Salakhutdinov, R. & Tenenbaum, J. B. (2015a) Human-level concept learning through probabilistic program induction. Science 350(6266):1332–38.Google Scholar
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W. & Jackel, L. D. (1989) Backpropagation applied to handwritten zip code recognition. Neural Computation 1:541–51.Google Scholar
Liu, D., Wellman, H. M., Tardif, T., & Sabbagh, M. A. (2008). Theory of mind development in Chinese children: A meta-analysis of false-belief understanding across cultures and languages. Developmental Psychology 44(2):523–31. Available at: http://dx.doi.org/10.1037/0012-1649.44.2.523.Google Scholar
Lombrozo, T. (2016) Explanatory preferences shape learning and inference. Trends in Cognitive Sciences 20(10):748–59.Google Scholar
Loughnan, S. & Haslam, N. (2007) Animals and androids implicit associations between social categories and nonhumans. Psychological Science 18(2):116–21.CrossRefGoogle ScholarPubMed
McClelland, J. L., Botvinick, M. M., Noelle, D. C., Plaut, D. C., Rogers, T. T., Seidenberg, M. S. & Smith, L. B. (2010) Letting structure emerge: Connectionist and dynamical systems approaches to cognition. Trends in Cognitive Sciences 14(8):348–56.Google Scholar
McClelland, J. L., McNaughton, B. L. & O'Reilly, R. C. (1995) Why there are complementary learning systems in the hippocampus and neocortex: Insights from the successes and failures of connectionist models of learning and memory. Psychological Review 102(3):419–57.Google Scholar
Medin, D. L. & Ortony, A. (1989). Psychological essentialism. In: Similarity and analogical reasoning, ed. Vosniadou, S. & Ortony, A., pp. 179–95. Cambridge University Press.Google Scholar
Mikolov, T., Joulin, A. & Baroni, M. (2016) A roadmap towards machine intelligence. arXiv preprint 1511.08130. Available at: http://arxiv.org/abs/1511.08130.Google Scholar
Mnih, V., Heess, N., Graves, A. & Kavukcuoglu, K. (2014). Recurrent models of visual attention. Presented at the 28th Annual Conference on Neural Information Processing Systems, Montreal, Canada. In: Advances in Neural Information Processing Systems 27(NIPS 2014), ed. Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N. D. & Weinberger, K. Q.. Neural Information Processing Systems Foundation.Google Scholar
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglous, I., King, H., Kumaran, D., Wierstra, D. & Hassabis, D. (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529–33.Google Scholar
Moeslund, T. B., Hilton, A. & Krüger, V. (2006) A survey of advances in vision-based human motion capture and analysis. Computer Vision and Image Understanding 104(2):90–126.Google Scholar
Murphy, G. L. & Medin, D. L. (1985) The role of theories in conceptual coherence. Psychological Review 92(3):289–316.Google Scholar
Nakayama, K., Shimojo, S. & Silverman, G. H. (1989) Stereoscopic depth: Its relation to image segmentation, grouping, and the recognition of occluded objects. Perception 18:55–68.Google Scholar
Ong, D. C., Zaki, J. & Goodman, N. D. (2015) Affective cognition: Exploring lay theories of emotion. Cognition 143:141–62.CrossRefGoogle ScholarPubMed
Raposo, D., Santoro, A., Barrett, D. G. T., Pascanu, R., Lillicrap, T. & Battaglia, P. (2017) Discovering objects and their relations from entangled scene representations. Presented at the Workshop Track at the International Conference on Learning Representations, Toulon, France, April 24–26, 2017. arXiv preprint 1702.05068. Available at: https://openreview.net/pdf?id=Bk2TqVcxe.Google Scholar
Real, E., Moore, S., Selle, A., Saxena, S., Suematsu, Y. L., Le, Q. & Kurakin, A. (2017) Large-scale evolution of image classifiers. arXiv preprint 1703.01041. Available at: https://arxiv.org/abs/1703.01041.Google Scholar
Reed, S. & de Freitas, N. (2016) Neural programmer-interpreters. Presented at the 4th International Conference on Learning Representations (ICLR), San Juan, Puerto Rico, May 2–5, 2016. arXiv preprint 1511.06279. Available at: https://arxiv.org/abs/1511.06279.Google Scholar
Rezende, D. J., Mohamed, S., Danihelka, I., Gregor, K. & Wierstra, D. (2016) One-shot generalization in deep generative models. Presented at the International Conference on Machine Learning, New York, NY, June 20–22, 2016. Proceedings of Machine Learning Research 48:1521–29.Google Scholar
Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D. & Lillicrap, T. (2016). Meta-learning with memory-augmented neural networks. Presented at the 33rd International Conference on Machine Learning, New York, NY, June 19–24, 2016. Proceedings of Machine Learning Research 48:1842–50.Google Scholar
Schulz, L. (2012a) Finding new facts; thinking new thoughts. Rational constructivism in cognitive development. Advances in Child Development and Behavior 43:269–94.Google Scholar
Schulz, L. (2012b) The origins of inquiry: Inductive inference and exploration in early childhood. Trends in Cognitive Sciences 16(7):382–89.Google Scholar
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., Driessche, G. V. D., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., Dieleman, S., Grewe, D., Nham, J., Kalchbrenner, N., Sutskever, I., Lillicrap, T., Leach, M., Kavukcuoglu, K, Graepel, T. & Hassabis, D. (2016) Mastering the game of go with deep neural networks and tree search. Nature 529(7585):484–89.Google Scholar
Socher, R., Perelygin, A., Wu, J. Y., Chuang, J., Manning, C. D., Ng, A. Y. & Potts, C. (2013) Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the Conference on EmpiricalMethods in Natural Language Processing (EMNLP), Seattle, WA, vol. 1631, p. 1642. Association for Computational Linguistics.Google Scholar
Spelke, E. S. (2003) What makes us smart? Core knowledge and natural language. Spelke ES. What makes us smart? Core knowledge and natural language. In: Language in mind: Advances in the Investigation of language and thought, ed. Gentner, D. & Goldin-Meadow, S., pp. 277–311. MIT Press.Google Scholar
Spelke, E. S. & Kinzler, K. D. (2007) Core knowledge. Developmental Science 10(1):89–96.CrossRefGoogle ScholarPubMed
Stanley, K. O. & Miikkulainen, R. (2002) Evolving neural networks through augmenting topologies. Evolutionary Computation 10(2):99–127.Google Scholar
Sukhbaatar, S., Szlam, A., Weston, J. & Fergus, R. (2015) End-to-end memory networks. Presented at the 2015 Neural Information Processing Systems conference, Montreal, QC, Canada, December 7–12, 2015. In: Advances in neural information processing systems 28 (NIPS 2015), ed. Cortes, C., Lawrence, N. D., Lee, D. D., Sugiyama, M. & Garnett, R. [oral presentation]. Neural Information Processing Systems Foundation.Google Scholar
Tompson, J. J., Jain, A., LeCun, Y. & Bregler, C. (2014). Joint training of a convolutional network and a graphical model for human pose estimation. Presented at the 28th Annual Conference on Neural Information Processing Systems, Montreal, Canada. In: Advances in Neural Information Processing Systems 27(NIPS 2014), ed. Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N. D. & Weinberger, K. Q., pp. 1799–807. Neural Information Processing Systems Foundation.Google Scholar
Toshev, A. & Szegedy, C. (2014). Deeppose: Human pose estimation via deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, pp. 1653–60. IEEE.Google Scholar
Tsividis, P. A., Pouncy, T., Xu, J. L., Tenenbaum, J. B. & Gershman, S. J. (2017) Human learning in Atari. In: Proceedings of the Association for the Advancement of Artificial Intelligence (AAAI) Spring Symposium on Science of Intelligence: Computational Principles of Natural and Artificial Intelligence, Stanford University, Palo Alto, CA, March 25–27, 2017. AAAI Press.Google Scholar
Ullman, T. D., Baker, C. L., Macindoe, O., Evans, O., Goodman, N. D. & Tenenbaum, J. B. (2009). Help or hinder: Bayesian models of social goal inference. Presented at the 2009 Annual Conference on Neural Information Systems Processing, Vancouver, BC, Canada, December 7–10, 2009. In: Advances in Neural Information Processing Systems 22 (NIPS 2009), ed. Bengio, Y., Schuumans, D., Lafferty, J. D., Williams, C. K. I. & Culotta, A.. Neural Information Processing Systems Foundation.Google Scholar
Vinyals, O., Blundell, C., Lillicrap, T. & Wierstra, D. (2016) Matching networks for one shot learning. Vinyals, O., Blundell, C., Lillicrap, T. Kavukcuoglu, K. & Wierstra, D. (2016). Matching networks for one shot learning. Presented at the 2016 Neural Information Processing Systems conference, Barcelona, Spain, December 5–10, 2016. In: Advances in Neural Information Processing Systems 29 (NIPS 2016), ed. Lee, D. D., Sugiyama, M., Luxburg, U. V., Guyon, I. & Garnett, R., pp. 3630–38. Neural Information Processing Systems Foundation.Google Scholar
Wellman, H. M. & Gelman, S. A. (1992) Cognitive development: Foundational theories of core domains. Annual Review of Psychology 43:337–75.Google Scholar
Wellman, H. M. & Gelman, S. A. (1998). Knowledge acquisition in foundational domains. In: Handbook of child psychology: Vol. 2. Cognition, perception, and language development, 5th ed., series ed. Damon, W., vol. ed. Damon, W., pp. 523–73. Wiley.Google Scholar
Weston, J., Chopra, S. & Bordes, A. (2015b) Memory networks. Presented at the International Conference on Learning Representations, San Diego, CA, May 7–9, 2015. arXiv:1410.3916. Available at: https://arxiv.org/abs/1410.3916.Google Scholar
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R. & Bengio, Y. (2015) Show, attend and tell: Neural image caption generation with visual attention. Presented at the 2015 International Conference on Machine Learning. Proceedings of Machine Learning Research 37:2048–57.Google Scholar